JP2018120567A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2018120567A5 JP2018120567A5 JP2017110899A JP2017110899A JP2018120567A5 JP 2018120567 A5 JP2018120567 A5 JP 2018120567A5 JP 2017110899 A JP2017110899 A JP 2017110899A JP 2017110899 A JP2017110899 A JP 2017110899A JP 2018120567 A5 JP2018120567 A5 JP 2018120567A5
- Authority
- JP
- Japan
- Prior art keywords
- factor
- pattern
- morpheme
- sequence
- settlement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000000877 morphologic Effects 0.000 claims description 6
- 238000000034 method Methods 0.000 claims 1
- 239000000203 mixture Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Description
本発明は、かかる事情に鑑みてなされたものであり、その目的は、決算関連情報からの要因抽出を効率的かつ柔軟に行い、投資家や機関投資家にとって有用な情報を提供することである。 The present invention has been made in view of such circumstances, and its object is had efficiently and flexibly row factors extracted from financial-related information, to provide information useful to investors and institutional investors is there.
かかる課題を解決すべく、第1の発明は、パターン記憶部と、文書解析部と、レポート作成部とを有し、決算関連情報を分析する決算分析システムを提供する。パターン記憶部には、要因パターンが記憶されている。この要因パターンは、少なくとも科目および金額情報を含む会計上の事象の表現と、この事象の要因の表現とを有する。文書解析部は、処理対象となる文の形態素列と、パターン記憶部に記憶された要因パターンとを比較する。処理対象となる文の形態素列は、この形態素列を構成する形態素またはその組み合わせに対して、少なくとも科目および金額を分類する属性毎に固有の属性ラベルを付与することによって抽象化されている。また、文書解析部は、要因パターンと一致した形態素列について、この要因パターンによって指定された部分を要因として抽出し、抽出された要因を形態素列における科目および金額情報と紐付けて、1組のデータとして記憶する。レポート作成部は、1組のデータに基づいて、決算分析レポートを出力する。 In order to solve such a problem, a first invention provides a settlement analysis system that includes a pattern storage unit, a document analysis unit, and a report creation unit and analyzes settlement-related information. The pattern storage unit stores a factor pattern. The factor pattern has an expression of an accounting event including at least the item and amount information, and an expression of a factor of the event. The document analysis unit compares the morpheme sequence of the sentence to be processed with the factor pattern stored in the pattern storage unit. The morpheme sequence of the sentence to be processed is abstracted by assigning a unique attribute label to each morpheme constituting the morpheme sequence or a combination thereof, at least for each attribute for classifying the subject and the amount of money. In addition, the document analysis unit extracts a part specified by the factor pattern as a factor from the morpheme string that matches the factor pattern, associates the extracted factor with the item and amount information in the morpheme string, and creates a set of Store as data. The report creation unit outputs a settlement analysis report based on one set of data.
また、第2の発明は、少なくとも科目および金額情報を含む会計上の事象の表現と、この事象の要因の表現とを有する要因パターンが予め記憶されているコンピュータを用いて、決算関連情報を分析する決算分析プログラムを提供する。このプログラムは、以下の第1から第3のステップを有する処理をコンピュータに実行させる。第1のステップでは、処理対象となる文の形態素列と、パターン記憶部に記憶された要因パターンとを比較する。処理対象となる文の形態素列は、この形態素列を構成する形態素またはその組み合わせに対して、少なくとも科目および金額を分類する属性毎に固有の属性ラベルを付与することによって抽象化されている。第2のステップでは、要因パターンと一致した形態素列について、この要因パターンによって指定された部分を要因として抽出し、抽出された要因を形態素列における科目および金額情報と紐付けて、1組のデータとして記憶する。第3のステップでは、1組のデータに基づいて、決算分析レポートを出力する。 Further, the second invention analyzes settlement-related information using a computer in which a factor pattern having at least an accounting event expression including at least item and amount information and an event factor expression is stored in advance. To provide a financial analysis program. This program causes a computer to execute processing having the following first to third steps. In the first step, the morpheme sequence of the sentence to be processed is compared with the factor pattern stored in the pattern storage unit. The morpheme sequence of the sentence to be processed is abstracted by assigning a unique attribute label to each morpheme constituting the morpheme sequence or a combination thereof, at least for each attribute for classifying the subject and the amount of money. In the second step, for a morpheme sequence that matches the factor pattern, a part specified by the factor pattern is extracted as a factor, and the extracted factor is associated with the item and amount information in the morpheme sequence to form a set of data. To be stored. In the third step, a settlement analysis report is output based on one set of data.
本発明によれば、文そのものではなく、文を形態素解析した上で属性ラベルによって抽象化された形態素列が、予め定義された要因パターンと比較される。そして、両者が一致した場合、この形態素列のうち、要因パターンによって指定された部分が要因として抽出される。要因パターンとの比較を属性ラベルによって抽象化された形態素列ベースで行うことで、定義すべき要因パターンの数を有効に抑制でき、要因抽出を効率的かつ柔軟に行うことが可能となる。それとともに、科目、金額情報および要因を紐付けて1組のデータとして記憶し、これに基づいて決算分析レポートを出力することで、資家や機関投資家にとって有用な情報を提供できる。 According to the present invention, not a sentence itself, but a morphological analysis of a sentence, and a morphological sequence abstracted by an attribute label are compared with a predefined factor pattern. Then, when the two match, the part specified by the factor pattern in the morpheme sequence is extracted as the factor. By performing the comparison with the factor pattern based on the morpheme sequence abstracted by the attribute label, the number of factor patterns to be defined can be effectively suppressed, and the factor extraction can be performed efficiently and flexibly. At the same time, the subject, the amount information, and the factor are linked and stored as a set of data, and a financial analysis report is output based thereon, thereby providing useful information for investors and institutional investors.
Claims (2)
少なくとも科目および金額情報を含む会計上の事象の表現と、当該事象の要因の表現とを有する要因パターンを記憶するパターン記憶部と、
処理対象となる文の形態素列であって、この形態素列を構成する形態素またはその組み合わせに対して、少なくとも科目および金額を分類する属性毎に固有の属性ラベルを付与することによって抽象化された形態素列と、前記パターン記憶部に記憶された前記要因パターンとを比較すると共に、前記要因パターンと一致した前記形態素列について、前記要因パターンによって指定された部分を要因として抽出し、当該抽出された要因を前記形態素列における科目および金額情報と紐付けて、1組のデータとして記憶する文書解析部と、
前記1組のデータに基づいて、決算分析レポートを出力するレポート作成部と
を有することを特徴とする決算分析システム。 In the settlement analysis system that analyzes settlement-related information,
A pattern storage unit that stores a factor pattern having at least an accounting event expression including subject and amount information, and an expression of a factor of the event;
A morpheme sequence of a sentence to be processed, and a morpheme abstracted by assigning a unique attribute label to each morpheme or a combination of the morphemes constituting the morpheme sequence, at least for each attribute for classifying the subject and the amount of money. A column is compared with the factor pattern stored in the pattern storage unit, and a part specified by the factor pattern is extracted as a factor for the morphological sequence that matches the factor pattern, and the extracted factor is A document analysis unit that stores the data as a set of data in association with the subject and amount information in the morphological sequence;
A settlement analysis system, comprising: a report creation unit that outputs a settlement analysis report based on the set of data .
処理対象となる文の形態素列であって、この形態素列を構成する形態素またはその組み合わせに対して、少なくとも科目および金額を分類する属性毎に固有の属性ラベルを付与することによって抽象化された形態素列と、前記パターン記憶部に記憶された前記要因パターンとを比較する第1のステップと、
前記要因パターンと一致した前記形態素列について、前記要因パターンによって指定された部分を要因として抽出し、当該抽出された要因を前記形態素列における科目および金額情報と紐付けて、1組のデータとして記憶する第2のステップと、
前記1組のデータに基づいて、決算分析レポートを出力する第3のステップと
を有する処理を前記コンピュータに実行させることを特徴とする決算分析プログラム。 In a settlement analysis program for analyzing settlement-related information, using a computer in which an expression of an accounting event including at least the subject and amount information and a factor pattern having an expression of a factor of the event are stored in advance,
A morpheme sequence of a sentence to be processed, and a morpheme abstracted by assigning a unique attribute label to each morpheme or a combination of the morphemes constituting the morpheme sequence, at least for each attribute for classifying the subject and the amount of money. A first step of comparing a column with the factor pattern stored in the pattern storage unit;
For the morphological sequence that matches the factor pattern, a part specified by the factor pattern is extracted as a factor, and the extracted factor is linked with the item and amount information in the morphological sequence and stored as a set of data. A second step to
A result analysis program which causes the computer to execute a process having a third step of outputting a result analysis report based on the set of data .
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017110899A JP6889038B2 (en) | 2017-01-23 | 2017-06-05 | Financial results analysis system and financial results analysis program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017009463A JP6155409B1 (en) | 2017-01-23 | 2017-01-23 | Financial analysis system and financial analysis program |
JP2017110899A JP6889038B2 (en) | 2017-01-23 | 2017-06-05 | Financial results analysis system and financial results analysis program |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2017009463A Division JP6155409B1 (en) | 2017-01-23 | 2017-01-23 | Financial analysis system and financial analysis program |
Publications (3)
Publication Number | Publication Date |
---|---|
JP2018120567A JP2018120567A (en) | 2018-08-02 |
JP2018120567A5 true JP2018120567A5 (en) | 2020-02-13 |
JP6889038B2 JP6889038B2 (en) | 2021-06-18 |
Family
ID=63045212
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2017110899A Active JP6889038B2 (en) | 2017-01-23 | 2017-06-05 | Financial results analysis system and financial results analysis program |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP6889038B2 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111324697B (en) * | 2020-02-19 | 2023-10-24 | 广东小天才科技有限公司 | Analysis management method and device for home education machine data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120284305A1 (en) * | 2010-01-19 | 2012-11-08 | Nec Corporation | Trend information search device, trend information search method and recording medium |
-
2017
- 2017-06-05 JP JP2017110899A patent/JP6889038B2/en active Active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Martin et al. | More efficient topic modelling through a noun only approach | |
US8892579B2 (en) | Method and system of data extraction from a portable document format file | |
US10592672B2 (en) | Testing insecure computing environments using random data sets generated from characterizations of real data sets | |
US10579372B1 (en) | Metadata-based API attribute extraction | |
WO2018059056A1 (en) | Service system data processing method and device | |
JP2017188137A5 (en) | ||
US10936637B2 (en) | Associating insights with data | |
JP2016085697A5 (en) | ||
JP2010123000A (en) | Web page group extraction method, device and program | |
JP2017041171A (en) | Test scenario generation support device and test scenario generation support method | |
US9064009B2 (en) | Attribute cloud | |
US9558462B2 (en) | Identifying and amalgamating conditional actions in business processes | |
US20170115856A1 (en) | Intelligent embedded experience gadget selection | |
Thaler et al. | Unsupervised signature extraction from forensic logs | |
JP6733366B2 (en) | Task estimation device, task estimation method, and task estimation program | |
US9703547B2 (en) | Computing program equivalence based on a hierarchy of program semantics and related canonical representations | |
US20230186212A1 (en) | System, method, electronic device, and storage medium for identifying risk event based on social information | |
JP2018120567A5 (en) | ||
Elkhidir et al. | Plagiarism detection using free-text fingerprint analysis | |
US20220215186A1 (en) | Machine learning enabled text analysis with support for unstructured data | |
Ali et al. | Detection of plagiarism in Urdu text documents | |
Zariquiey et al. | Untangling the evolution of body-part terminology in Pano: conservative versus innovative traits in body-part lexicalization | |
Susuri et al. | Machine learning based detection of vandalism in wikipedia across languages | |
JP2018077604A (en) | Artificial intelligence device automatically identifying violation candidate of achieving means or method from function description | |
JP6677158B2 (en) | Document data processing apparatus, document data processing method, and document data processing program |